efficient attention 1global-local context 1image super-resolution 1lightweight models 1vision transformers 1
From the 1 of 2 linked papers with an AI index.
2 papers
cs.CV2026
CUST: Clustered Unit-level Similarity Transformer for Lightweight Image Super-Resolution
Jeongsoo Kim
The paper introduces CUST, a lightweight Vision Transformer architecture for image super-resolution that combines global and local attention by clustering similar patches and using…
cs.CV2024
LMLT: Low-to-high Multi-Level Vision Transformer for Image Super-Resolution
Jeongsoo Kim, Jongho Nang, Junsuk Choe
Recent Vision Transformer (ViT)-based methods for Image Super-Resolution have demonstrated impressive performance. However, they suffer from significant complexity, resulting in hi…